korrents

korrents · piece

GPT-6 Astra, Looped Transformers, and Hidden Reasoning

Sebastian Raschka · 9 Sept 2026 · magazine.sebastianraschka.com ↗

3 korrents from this piece

Sebastian Raschka did not write this page.

Every claim below was made in this piece, quoted word for word and numbered in the order the piece makes them, so you can read it there rather than take our word for it. The sentence above each quote is our reading of the claim, not their wording. Each quote was checked against a stored copy of the page at build time; where the two differ, the quote is the fact.

  1. Our reading

    Computer-use capability will be a major focus of LLM and coding-agent development in the coming months and years.

    Their wordsI expect the upcoming months (or years) also to be an era of computer use refinement on both the LLM and the agent harness layer.

  2. Our reading

    Frontier language models will remain reasoning models trained with RLVR-style chain-of-thought for the foreseeable future.

    Their wordsGPT-6 Astra (and likely any LLM in the foreseeable future) is still a reasoning model.

  3. Our reading

    Looped/recurrent-depth transformer architectures can improve model quality at a fixed compute budget when the model is large enough.

    Their wordsSo, in short, we can say that using looped transformers can improve model quality at a fixed compute budget if the model is large enough.